© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39813
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devaient
    -0.62
     devront
    -0.62
     faisons
    -0.60
     parlent
    -0.60
     précédentes
    -0.58
     devriez
    -0.58
     associées
    -0.57
     NUKAT
    -0.56
     devrez
    -0.56
     pourrez
    -0.55
    POSITIVE LOGITS
     الاطلاع
    0.91
     the
    0.85
     its
    0.74
    AnchorStyles
    0.74
    AddTagHelper
    0.66
     a
    0.65
     indisponible
    0.63
     NSCoder
    0.63
     their
    0.62
     of
    0.56
    Activations Density 0.006%

    No Known Activations